Simulation Study of Audio Recognition for Equipment Fault Diagnosis
Xinze Zou, Yuxuan Cao, Jun Jie Zhu, Kangli Zhu · 2023
In the country's heavy industry, as one of the key components of rotating machinery and equipment, bearings play an extremely important role. In the actual industrial production process, in order not to affect the normal operation of the entire mechanical equipment, we will try our best to avoid its failure, which is of great significance to the protection of life and property safety. To solve this problem, we propose a method that comprehensively considers the Mel frequency cepstral coefficient (MFCC) and wavelet packet energy, extracts the features generated in the chemical pump and other equipment of the bearing fault diagnosis plant, extracts its features, and uses MFCC template matching and energy distribution analysis to determine whether the equipment is operating normally. The analysis results show that this method can obtain better feature extraction effect and recognition rate.